Research map / Image generation / Editing and style transfer
A Style-Aware Discriminator for Controllable Image Translation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Integrate the style encoder with the discriminator instead of using separate modules (ablation) | Style-aware discriminator on AFHQ · AFHQ | mFID: 159.7 -> 14.7 | Helped |
| Integrate the style encoder with the discriminator instead of using separate modules (ablation) | Style-aware discriminator on AFHQ · AFHQ | k-NN accuracy: 80.6 -> 99.1 | Helped |
| Use color distortion during training (ablation) | Style-aware discriminator · Image translation | style representation of color | Hurt |
| Remove cutout augmentation (ablation) | Style-aware discriminator on human-face datasets · Human-face image translation | attribute representation | Hurt |
| Vary the number of prototypes (ablation) | AdaIN-based model · AFHQ | mFID | Mixed |
Closest papers by meaning
- Memory-Guided Unsupervised Image-to-Image Translation (CVPR 2021 · similarity 0.90)
- Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation (CVPR 2021 · similarity 0.89)
- Image-to-Image Translation via Hierarchical Style Disentanglement (CVPR 2021 · similarity 0.88)
- Style-Guided and Disentangled Representation for Robust Image-to-Image Translation (AAAI 2022 · similarity 0.88)
- StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements (CVPR 2025 · similarity 0.85)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.